R Notebook
Description about the Project
Setup:
Data:
Parliamentarians
Tweets
Data processing
Plots:
Word Cloud of commonly used hashtags of german german political paries in 2021
ggplot(topHashtags,
aes(label = hashtags,
size = no_hashtags
)
) +
geom_text_wordcloud_area(area_corr = TRUE, shape = "square", rm_outside = T, area_corr_power = 1) +
# To revert, change rm_outside to FALSE and max_size to 15
scale_size_area(max_size = 19) +
theme_minimal() +
scale_color_gradient(low = "black", high = "lightblue") +
labs(title = "Die meist verwendeten Hashtags der Parteien") +
facet_wrap(~Partei)## Some words could not fit on page. They have been removed.
## Some words could not fit on page. They have been removed.
## Some words could not fit on page. They have been removed.
## Some words could not fit on page. They have been removed.
## Some words could not fit on page. They have been removed.
## Some words could not fit on page. They have been removed.
Twitter Usage per state in 2021 (Map test)
# References:
# https://cran.r-project.org/web/packages/leaflet.minicharts/vignettes/introduction.html
# https://r-spatial.github.io/mapview/articles/articles/mapview_04-popups.html
mapData = mainDataWithState %>%
group_by(Bundesland) %>%
mutate(Partei, Partei = case_when(
Partei == "CSU"~"CDU/CSU",
Partei == "CDU"~"CDU/CSU",
Partei == "FDP/DVP"~"FDP",
Partei == "FW"~"Andere",
Partei == "fraktionslos"~"Andere",
TRUE ~ Partei
)) %>%
dplyr::mutate(
no_tweets = n()
) %>%
dplyr::select(Bundesland, no_tweets) %>%
distinct(Bundesland, .keep_all=TRUE) %>%
filter(Bundesland != "Deutschland") %>%
filter(Bundesland != "EU-Parlament")
top3Hashtags = topHashtags %>%
group_by(Bundesland, Partei) %>%
slice_max(order_by = no_hashtags, n = 3)
nestedHashtags = top3Hashtags %>%
dplyr::select(Partei, Bundesland, hashtags) %>%
group_by(Partei, Bundesland) %>%
nest() %>%
group_by(Bundesland) %>%
nest()
hashtagHTML = top3Hashtags %>%
ungroup() %>%
dplyr::select(-screen_name) %>%
group_by(Bundesland, Partei) %>%
mutate(hashtags3 = paste0("#", hashtags, collapse = ", ")) %>%
mutate(partei = paste0("<strong>",Partei,": </strong>")) %>%
distinct(Partei, Bundesland, .keep_all=TRUE) %>%
mutate(html = paste0(partei, hashtags3, "<br>")) %>%
group_by(Bundesland) %>%
mutate(html = paste0(html, collapse = "")) %>%
distinct(Bundesland, html)
#mutate(hashtags3 = paste0(html,hashtags,"<br>", collapse = ", "))
# Load map data from GADM
de_map <-
getData("GADM", country="Germany", level=1, path='./data/mapfiles') %>%
st_as_sf() %>%
left_join(mapData, by = c("NAME_1" = "Bundesland")) %>%
left_join(hashtagHTML, by = c("NAME_1" = "Bundesland"))
# dplyr::select() - waiting for dataframe
cuts <- c(0, 20000, 40000, 60000, 80000, 100000, 120000, 140000, 160000, 180000)
pal <- colorBin("PuBu", domain = de_map$no_tweets, bins = cuts)
# Hard coded Version
popup <- paste("<strong>Anzahl der Tweets in </strong>",
"<strong>", de_map$NAME_1, ": </strong>", "<br>", de_map$no_tweets,
"<br>", "<br>",
"<b> Top 3 Hashtags pro Partei: </b>", "<br>",
de_map$html)
mapTest <-
leaflet(data = de_map) %>%
addProviderTiles(providers$CartoDB.Voyager) %>%
setView(lng = 10.4507147, lat = 50.9833118, zoom = 5) %>%
addPolygons(data = de_map,
fillColor= ~pal(no_tweets),
fillOpacity = 0.8,
weight = 0.5,
label = de_map$NAME_1,
color = "black",
popup = popup) %>%
addLegend("bottomright",
pal = pal,
values = de_map$no_tweets,
title = "Anzahl der Tweets",
opacity = 1)
mapTestPie Chart
missingTwitterUsers = tibble(User = scrapedTweetsPerUser) %>%
mutate(tweets = map_int(User, nrow)) %>%
mutate(usernames = names(scrapedTweetsPerUser)) %>%
dplyr::select(-User) %>%
mutate(missing = ifelse(tweets == 0, "Fehlende Twitter Daten", "Twitter Daten vorhanden"))
# ggplot version
ggplot(missingTwitterUsers, aes(x="", y=missing, fill=missing)) +
geom_bar(stat="identity", width=1) +
coord_polar("y", start=0)
# plotly version
pieColors <- c("Twitter Daten Vorhanden" = "000000",
"Fehlende Twitter Daten" = "ece7f2")
plot_ly(
missingTwitterUsers,
labels = ~missing,
type = "pie",
textinfo = "percentage",
textposition = "inside",
marker = list(colors = ~pieColors)
) %>%
layout(title = "Anteil von vorhandenen Twitter Daten")# to do: count is one, change color, add text and fix legend
stackedBarData = mainData %>%
left_join(missingTwitterUsers, by = c("SM_Twitter_user" = "usernames" )) %>%
filter(Kategorie != "EU-Parlament") %>%
mutate(missing = replace_na(missing, "Kein Account")) %>%
dplyr::select(Name, Partei, missing) %>%
mutate(Partei, Partei = case_when(
Partei == "CSU"~"CDU/CSU",
Partei == "CDU"~"CDU/CSU",
Partei == "FDP/DVP"~"FDP",
Partei == "FW"~"Andere",
Partei == "fraktionslos"~"Andere",
Partei == "SSW"~"Andere",
Partei == "BIW"~"Andere",
Partei == "BVB/FW"~"Andere",
TRUE ~ Partei
)) %>%
group_by(Partei) %>%
dplyr::mutate(
count = 1
)
options(scipen = 999)
stackedBar <-
ggplot(stackedBarData, aes(fill=missing, y=count, x=Partei)) +
geom_bar(position="stack",
stat="identity") +
scale_fill_manual("", values = c("#ece7f2", "#a6bddb", "#2b8cbe")) +
ggtitle("Verteilung von Twitter Konten pro Partei") +
ylab("Anzahl der Konten") +
xlab("") +
theme(panel.background = element_blank())
ggplotly(stackedBar)plot_ly(stackedBarData,
x = ~Partei,
y = ~count,
hovertemplate = "my value: %{y}",
type = "bar",
name = ~missing,
color = ~missing
) %>%
layout(yaxis = list(title = "count"),
barmode = "stack",
title = "Verteilung von Twitter Konten pro Partei")
Social Media usage of german political paries in 2021